Hi Ram,
On 12/01/17 02:36, Ankireddypalle Reddy wrote:
Xavi,
I added some more logging information. The trusted.ec.size field
values are in fact different.
trusted.ec.sizel1 = 62719407423488l2 = 0
That's very weird. Directories do not have this attribute. It's
On Wed, Jan 11, 2017 at 9:32 AM, Atin Mukherjee wrote:
>
>
>
>
> On Mon, Jan 9, 2017 at 1:56 PM, Samikshan Bairagya
> wrote:
>
>>
>>
>> On 01/09/2017 10:33 AM, Shyam wrote:
>>
>>> I am considering this as tentatively accepted for 3.10 release for the
Works fine for us Sriram. Friday 2-3 pm.
Regards,
Avra
On 01/12/2017 11:54 AM, sri...@marirs.net.in wrote:
Hi Avra,
Sorry for the late reply, could we have the meeting tomorrow? 2-3 pm?
Sriram
On Wed, Jan 11, 2017, at 11:58 AM, Avra Sengupta wrote:
Hi,
We can have a discussion tomorrow
Hi Avra,
Sorry for the late reply, could we have the meeting tomorrow? 2-3 pm?
Sriram
On Wed, Jan 11, 2017, at 11:58 AM, Avra Sengupta wrote:
> Hi,
>
> We can have a discussion tomorrow i.e 12th January from 3pm to 4 pm.
> Does that time work for you?
>
> Meeting Link :
cc'ing devel as well for some developer insight..
-- Forwarded message --
To: gluster-users
I had a question on the expected behaviour of simple distributed volumes
when a brick fails for the following scenarios (as in, will the scenario
succeed for
Xavi,
I added some more logging information. The trusted.ec.size field
values are in fact different.
trusted.ec.sizel1 = 62719407423488l2 = 0
This is a fairly static setup with no brick/ node failure. Please
explain why is that a heal is
Xavi,
I built a debug binary to log more information. This is what is
getting logged. Looks like it is the attribute trusted.ec.size which is
different among the bricks in a sub volume.
In glustershd.log :
[2017-01-11 14:19:45.023845] N [MSGID: 122029]
erfs-3.9.1
- Open bugs :
https://bugzilla.redhat.com/showdependencytree.cgi?maxdepth=2=glusterfs-3.9.0_resolved=1
- Roadmap : https://www.gluster.org/community/roadmap/3.9/
- Updates:
- I will try to tag 3.9.1 today (20170111) or tomorrow. (delayed
from 20161220, or early for 20170120, depending
> To avoid a DHT problem ;) it maybe better to take this sorted list and
> assign tests in a cyclic fashion so that all chunks relatively take the
> same amount of time to complete, than it being skewed due to the hash?
I assume you don't really mean cyclic, because that would *guarantee* a
On 11/01/2017 8:13 PM, Kaushal M wrote:
[1]:https://github.com/gluster/glusterfs/blob/release-3.7/doc/release-notes/3.7.18.md
Is there a reason that "performance.strict-o-direct=on" needs to be set
for VM Hosting?
--
Lindsay Mathieson
___
On Wed, Jan 11, 2017 at 3:43 PM, Kaushal M wrote:
> GlusterFS 3.7.19 is a regular bug fix release for GlusterFS-3.7. The
> release-notes for this release can be read here[1].
>
> The release tarball and community provided packages[2] can obtained
> from
+gluster-users
Milind
On 01/11/2017 03:21 PM, Milind Changire wrote:
The management connection uses network.ping-timeout to time out and
retry connection to a different server if the existing connection
end-point is unreachable from the client.
Due to the nature of the parameters involved in
GlusterFS 3.7.19 is a regular bug fix release for GlusterFS-3.7. The
release-notes for this release can be read here[1].
The release tarball and community provided packages[2] can obtained
from download.gluster.org[3]. The CentOS Storage SIG[4] packages have
been built and should be available
Today's meeting is due to start in 2 hours from now at 1200UTC in
#gluster-meeting on Freenode.
The meeting agenda and update pad is at [1]. Add updates and topics
for discussion here.
See you all in 2 hours.
~kaushal
[1]: https://bit.ly/gluster-community-meetings
Jeff, Nigel,
We do get time a test takes to run, as a part of the output of the test
runs (at least on CentOS runs as I checked here [1]).
To avoid a DHT problem ;) it maybe better to take this sorted list and
assign tests in a cyclic fashion so that all chunks relatively take the
same
The management connection uses network.ping-timeout to time out and
retry connection to a different server if the existing connection
end-point is unreachable from the client.
Due to the nature of the parameters involved in the TCP/IP network
stack, it becomes imperative to control the other
16 matches
Mail list logo